1) fuzzy mean error
模糊均差
1.
According to characteristics of medical images,in order to find more suited algorithms for estimating the standard variance,this paper presented a novel algorithm to estimate noise standard variation by fuzzy mean error instead of variance.
针对医学图像的特点、基于寻找更合适的噪声标准差估计方法,本研究提出了一种新的利用模糊均差代替普通标准方差估计噪声标准差的方法。
2) fuzzy mean variance
模糊均方差
1.
In the method, the probabilities of states and the benefits of projects were expressed in the forms of triangular fuzzy numbers,and the approach to calculating fuzzy expected benefit, fuzzy mean variance and fuzzy variance coefficient were presented.
依据以往风险性投资决策分析的基本原理和风险投资项目的特点 ,提出了一种带有模糊信息的风险投资项目决策方法·在该方法中 ,状态概率和项目收益将采用三角模糊数来表示 ,并且给出了项目的模糊期望收益、项目收益的模糊均方差及模糊变异系数的定义和计算方法 ,同时为了便于项目选择和排序 ,还进一步给出了将模糊数映射为期望值的简捷计算公式·该方法克服了以往风险性投资决策分析方法的不足 ,拓宽了应用范围·最后给出了一个算例
3) residual error model of fuzzy average-generated function (REMFAF)
模糊均生函数残差模型
1.
On the basis of fuzzy average-generated function model (FAFM), its residual error data series has been used to calibrate FAFM, and residual error model of fuzzy average-generated function (REMFAF) has been presented and the method of model accuracy validation has also been given.
在模糊均生函数模型(FAFM)基础上,利用其残差数据序列对FAFM进行校正,提出了模糊均生函数残差模型(REMFAF),给出了模型预报精度的检验方法。
4) difference of mean smoothed image
均值模糊差分图像
1.
To solve the problems of instability to view direction and large computational burden of scale invariant feature transform(SIFT),a fast scale invariant feature extraction method is proposed by using the difference of mean smoothed images which is an approximation of the well-known difference of Gaussian to build the scale space.
针对尺度不变特征(SIFT)对观测视角不稳定且计算量大的缺点,利用均值模糊差分图像来近似高斯差分图像,提出了一种快速尺度不变特征提取方法;根据局部平面区域的仿射变换关系,提出了一种在多幅连续观测图像中根据灰度梯度直接计算局部平面方向的方法,并利用特征所在局部平面的方向,为特征创建了一个具有仿射不变的描述器;同时将新提出的基于局部平面的仿射不变特征(LPAIF)应用于基于单目视觉的同时定位与地图创建(SLAM)中。
补充资料：差差
1.犹参差。不齐貌。
说明：补充资料仅用于学习参考，请勿用于其它任何用途。
参考词条